Summary of the paper

Title Sentence Rephrasing for Parsing Sentences with OOV Words
Authors Hen-Hsen Huang, Huan-Yuan Chen, Chang-Sheng Yu, Hsin-Hsi Chen, Po-Ching Lee and Chun-Hsun Chen
Abstract This paper addresses the problems of out-of-vocabulary (OOV) words, named entities in particular, in dependency parsing. The OOV words, whose word forms are unknown to the learning-based parser, in a sentence may decrease the parsing performance. To deal with this problem, we propose a sentence rephrasing approach to replace each OOV word in a sentence with a popular word of the same named entity type in the training set, so that the knowledge of the word forms can be used for parsing. The highest-frequency-based rephrasing strategy and the information-retrieval-based rephrasing strategy are explored to select the word to replace, and the Chinese Treebank 6.0 (CTB6) corpus is adopted to evaluate the feasibility of the proposed sentence rephrasing strategies. Experimental results show that rephrasing some specific types of OOV words such as Corporation, Organization, and Competition increases the parsing performances. This methodology can be applied to domain adaptation to deal with OOV problems.
Topics Tools, Systems, Applications, Other
Full paper Sentence Rephrasing for Parsing Sentences with OOV Words
Bibtex @InProceedings{HUANG14.60,
  author = {Hen-Hsen Huang and Huan-Yuan Chen and Chang-Sheng Yu and Hsin-Hsi Chen and Po-Ching Lee and Chun-Hsun Chen},
  title = {Sentence Rephrasing for Parsing Sentences with OOV Words},
  booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)},
  year = {2014},
  month = {may},
  date = {26-31},
  address = {Reykjavik, Iceland},
  editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {978-2-9517408-8-4},
  language = {english}
 }
Powered by ELDA © 2014 ELDA/ELRA